TEST #818 RESULTS
05/04/2025 - 12:17 PM
ACCELERATOR
MODEL
49.5
tokens/s
generation
869
ms
time to first token
1515
tokens/s
prompt
442
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11700F @ 2.50GHz (rocketlake)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1760
tokens/s
51.0
tokens/s
601
ms
pp4096+tg256
1404
tokens/s
44.4
tokens/s
2.94
sec
pp2048+tg256
1620
tokens/s
49.0
tokens/s
1.28
sec
pp2048+tg768
1619
tokens/s
48.4
tokens/s
1.29
sec
pp1024+tg1024
1765
tokens/s
50.4
tokens/s
599
ms
pp1280+tg3072
1710
tokens/s
47.3
tokens/s
770
ms
pp384+tg1152
1869
tokens/s
51.4
tokens/s
225
ms
pp64+tg1024
1427
tokens/s
51.9
tokens/s
64
ms
pp16+tg1536
462
tokens/s
51.5
tokens/s
54
ms